Research and Publications
|
|
Accelerating Deep Learning using Ivy
Guillermo Sanchez-Brizuela,
Ved Patwardhan,
Matthew Barrett,
Paul Anderson,
Mustafa Hani,
Daniel lenton,
NeurIPS, 2023
paper /
video /
code /
docs
Ivy enables the integration of code from one ML framework into another, speeding up development and also model inference.
|
|
End-to-End Egospheric Spatial Memory
Daniel lenton,
Stephen James,
Ronald Clark,
Andrew Davison
International Conference on Learning Representations (ICLR), 2021
paper /
video /
code /
project page
ESM encodes the memory in an ego-sphere around the agent, enabling expressive 3D representations.
ESM can be trained end-to-end via either imitation or reinforcement learning,
and improves both training efficiency and final performance against other memory baselines on visuomotor control tasks.
|
|
Unsupervised Path Regression Networks
Michal Pandy,
Daniel lenton,
Ronald Clark
International Conference on Intelligent Robots and Systems (IROS), 2021
paper /
project page
We demonstrate that challenging shortest path problems can be solved via direct spline
regression from a neural network, trained in an unsupervised manner without requiring
ground truth optimal paths for training. To achieve this, we derive a geometry-dependent
optimal cost function whose minima guarantees collision-free solutions.
|
|
Waypoint Planning Networks
Alexandru-Iosif Toma,
Hussein Ali Jaafar,
Hao-Ya Hsueh,
Stephen James,
Daniel lenton,
Ronald Clark,
Sajad Saeedi,
International Conference on Computer Vision and Robotics (CVR), 2021
paper /
video /
code /
project page /
Waypoint Planning Networks, or WPN, is a hybrid motion planning algorithm based on LSTMs with
a local kernel, a classic algorithm such as A*, and a global kernel using a learned
algorithm. WPN produces a more computationally efficient and robust solution than other
learned approaches.
|
|
MoreFusion: Multi-object Reasoning for 6D Pose Estimation from Volumetric
Fusion
Kentaro Wada,
Edgar Sucar,
Stephen James,
Daniel lenton,
Andrew Davison
Conference on Computer Vision and Pattern Recognition (CVPR), 2020
paper /
video /
code /
project page
MoreFusion makes 3D object pose proposals from single RGB-D views,
accumulates pose estimates and non-parametric occupancy information from multiple views as
the camera moves,
and performs joint optimization to estimate consistent, non-intersecting poses for multiple
objects in contact.
|
|